drag

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare destructiveHint=false, so the description carries the transparency burden. It discloses the human-like curved path, the requirement that both ends be on screen, and the return of from/to points. However, it does not describe error behavior or prerequisites like element interactability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each earning its place: first states the action, second explains parameter choices, third adds constraints and output. No extraneous words; front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 6 parameters, 1 required, low schema coverage, and no output schema, the description provides adequate context for most use cases. It covers two drag modes, preconditions, and output, though it omits behavior for edge cases or details about frameId.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 17% (only returnSnapshot has a description). The tool description explains target (element to press), toTarget (drop target), and dx/dy (pixel offset), adding value. But frameId is left ambiguous, and the explanation for dx/dy is brief, leaving some parameters underspecified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs a drag action: pressing, moving with a human-like curved path, and releasing. It distinguishes two drag modes (toTarget for elements, dx/dy for offsets), which differentiates it from siblings like click or hover.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs to give exactly one destination (toTarget or dx/dy), which guides correct parameter choice. It also specifies that both ends must be on screen, providing a precondition, but does not mention when not to use the tool or alternatives beyond the constraint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.